Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/arylmera/token-dashboard/claude-mdgit clone --depth 1 https://github.com/Arylmera/Token-DashboardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/arylmera/token-dashboard/claude-md)<a href="https://agentmods.dev/instructions/arylmera/token-dashboard/claude-md"><img src="https://agentmods.dev/badge/instructions/arylmera/token-dashboard/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02495 | $0.02495 |
| Opus 5 | $0.01247 | $0.01247 |
| Sonnet 5 | $0.00499 | $0.00499 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
Token-Dashboard CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code when working in this repository.
Project overview
Token Dashboard — a local desktop dashboard for tracking Claude Code token usage, costs, and session history. Reads the JSONL transcripts Claude Code writes to ~/.claude/projects/ and turns them into per-prompt cost analytics, tool/file heatmaps, subagent attribution, cache analytics, project comparisons, and a rule-based tips engine.
Inspired by phuryn/claude-usage but diverges in UI (React 18 bundled with esbuild, dark theme, hash router, SSE refresh) and scope (expensive-prompt drill-down, skills view, tips engine, streaming-snapshot dedup). See docs/inspiration.md for the original's feature set.
Status
5.0 line — Rust + Tauri. The 3.x Python + Electron stack is no longer in the tree; existing 3.x users keep their installed builds, future development targets v5 only. Workspace builds clean on cargo build --workspace; ~180 tests across core + cli (run cargo test --workspace for the live count). Tauri shell verified on Windows; macOS and Linux QA happens via the release-tauri pipeline.
Architecture
crates/
token-dashboard-core/ scanner, db, queries, pricing, preferences,
tips, skills_catalog, anthropic_sync, sources.
No process model — just a library.
token-dashboard-cli/ axum router + tokio bin (`token-dashboard`).
Owns the /api/* surface and the SSE bus.
token-dashboard-tauri/ Tauri 2 desktop shell. Links the cli as a
library and calls app(state) directly inside
the tauri runtime — single process. The
analytics surface spawns no subprocess. The
src/live/ module (ported from Praetorium) is
the one exception: it drives the `claude` CLI
(process.rs) and watches ~/.claude/projects/
(session_watch.rs), streaming events to the
frontend over Tauri IPC channels.
praetorium-core/ Pure parser/vault library (no Tauri, no db,
no async runtime) backing the Live feature.
frontend/ React 18 + esbuild (`entry.jsx` →
`frontend/dist/app.js`). The webview talks
directly to /api/* through the embedded
server; the SSE consumer in api-client.js
drives view refreshes.
docs/ plan, design, roadmap, inspiration.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 123 lines · 2,495 tokens per session scan A 02f25990ace0
Token-Dashboard CLAUDE.md is an instructions file published in the GitHub repository Arylmera/Token-Dashboard (10 stars, last pushed 7d ago), licensed MIT. It adds 2,495 tokens to every session, about $0.0125 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
agent-odometer AGENTS.md
Instructions for ekalb81/agent-odometer, covering agents.md, project purpose, before changing code, architecture boundaries and authorized outbound network.
agent-usage-desktop AGENTS.md
Instructions for hongshuo-wang/agent-usage-desktop, covering agents.md, build & run, desktop app (tauri), macos arm64 example and macos x8664.
agent-usage-desktop CLAUDE.md
Instructions for hongshuo-wang/agent-usage-desktop, a project described as: A desktop app for local usage, cost, throughput, and session analytics across Claude Code, Codex, OpenCode, and OpenClaw. | 在本地统一统计和分析 Claude Code、Codex、OpenCode 与 OpenClaw 的用量、费用、吞吐和会话。.
nextclaw AGENTS.md
AGENTS.md instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.
moonproxy-desktop AGENTS.md
AGENTS.md instructions for MoonProxyHQ/moonproxy-desktop, covering moonproxy, 功能, 技术栈, 目录结构 and 配置与数据存储.
code-by-wire CLAUDE.md
Instructions for luojiahai/code-by-wire, covering claude.md, development, website, architecture and code style.